Bedrock AgentCore (AWS)

https://aws.amazon.com/bedrock/agentcore/

AWS Bedrock AgentCore — managed runtime to deploy + scale + observe agents. Multi-component: Runtime, Identity, Memory, Gateway, Browser, Code Interpreter, Observability. Distinct from Bedrock Agents (older fixed-config product); AgentCore is the 2025 framework-agnostic runtime for any agent (LangGraph, CrewAI, Strands, OpenAI Agents SDK).

At a glance

Type
AWS-managed runtime + memory + tools for agents
Tier
T2
Created
2025-07
Latest release
not applicable — not OSS
License
not applicable — not OSS
GitHub
not applicable — no GitHub repo
Pricing
Usage-based AWS pricing
Funding
Amazon / AWS (parent)

Taxonomy

storage
kv
retrieval
similarity
persistence
long-term
update
agent-controlled
unit
fact
governance
opaque
conflict
llm-arbitrate

When to use

Optimised for: framework-agnostic AWS-managed agent runtime

Anti-fit: AWS-centric; preview-tier maturity; pricing complexity

Pros & cons

Pros

Only major-cloud-managed framework-agnostic agent runtime; OTel observability is first-class; chooses Mem0 as canonical memory provider.

Cons

Preview; AWS-only; pricing complexity inherited from AWS; lots of moving parts to learn (Runtime + Identity + Memory + ...).

Claims & capabilities

AWS-managed runtime preview Jul 2025; framework-agnostic; integrates with Strands Agents, Mem0 as memory provider.

Technical surface

API surface
AWS SDK (Python, JS, Java); Bedrock API
Backend storage
AWS-managed (DynamoDB, S3, OpenSearch under the hood)
Deployment
Cloud (AWS-managed)
Embedding model
not applicable — not a memory product
Multi-tenancy
AWS account isolation
MCP
searched not found
A2A
searched not found
OpenTelemetry
OpenTelemetry — AgentCore Observability is OTel-based

Similar systems

Other agent ides & coding harnesses in the catalog, ranked by inbound references.

  • Claude Code (Anthropic) T1

    Anthropic's official agentic coding CLI — runs Claude as a long-running coding agent in the developer's terminal. Memory layer = CLAUDE.md (project + user scoped), agent skills, MCP servers. Released GA October 2024; widely adopted as the reference harness for Claude-as-coder. Plan Mode and Compute Use surfaces extend it from coding to broader desktop automation.

  • GitHub Copilot (Agent Mode) T1

    The original AI coding assistant (Copilot in editor; 2021). 2025 evolved into a full agentic surface: chat, completions, Agent Mode (multi-step), and Copilot Workspace. Backed by Microsoft. Distinct row from Workspace — this row covers the everyday in-editor + agent mode product, Workspace covers the hosted spec-driven workflow.

  • Aider (harness) T2

    OSS terminal coding agent by Paul Gauthier — one of the original AI-pair-programmer CLIs (2023). Architect/Editor modes; repo-map for context; uses any LiteLLM-compatible model. Memory via CONVENTIONS.md and .aider.conf.yml — author-edited markdown. Distinct from the separate Aider memory-row in "Coding-agent memory"; this row characterises the harness itself.

  • Amazon Q Developer T1

    Amazon's developer-focused agent — formerly CodeWhisperer (renamed 2024-Q4). Available as IDE plugins (VS Code, JetBrains, Visual Studio, Eclipse), in AWS Console, and CLI. Strong AWS-tooling integration: Q can read CloudWatch, troubleshoot IAM, suggest AWS-SDK code. Companion to Kiro for spec-driven flows.

  • Anthropic Computer Use T1

    Anthropic's API-surface capability that lets Claude control a virtual desktop — see screenshots, type, click. Launched 2024-10 as a public beta. Not a finished IDE itself; it's the substrate that other harnesses (and Anthropic's own Claude apps) use to operate a computer.

  • Bolt.new (StackBlitz) — harness T1

    Cross-listing of Bolt.new at the harness layer. StackBlitz's WebContainer technology runs full Node.js in-browser; Bolt prompts the user for an app spec, then writes/edits/runs/deploys it entirely in-browser. The Coding-agent-memory row remains canonical for the memory framing.

Related systems

References (2)

  • Mem0 depends on at runtime — adjacent-infrastructure cell: AWS Bedrock; Mem0 (as memory provider); Strands Agents
  • Strands Agents (AWS) integrates with — framework-agnostic; integrates with Strands Agents, Mem0 as memory provider.

Referenced by (7)

  • Amazon Nova family depends on at runtime — adjacent-infrastructure cell: AWS Bedrock (distribution); Amazon Q Developer / Q Business; Alexa+; Trainium/Inferentia chips
  • Amazon Q Developer depends on at runtime — adjacent-infrastructure cell: AWS Bedrock; AWS IAM; CloudWatch
  • AWS Bedrock AgentCore Memory depends on at runtime — adjacent-infrastructure cell: requires AWS Bedrock + AgentCore
  • Kiro depends on at runtime — adjacent-infrastructure cell: AWS Bedrock (model routing); Anthropic Claude + Amazon Nova
  • Meta Llama 4 family depends on at runtime — adjacent-infrastructure cell: HuggingFace Transformers; vLLM; llama.cpp; Together AI; Groq; AWS Bedrock; Azure AI Foundry
  • Mistral Large 2 / Mixtral family depends on at runtime — adjacent-infrastructure cell: Mistral Le Chat consumer (separate row); Codestral for code agents; Mistral Forge on-prem; AWS Bedrock / Azure AI distribution
  • Strands Agents Memory (AWS) depends on at runtime — adjacent-infrastructure cell: requires AWS; Bedrock + Mem0 / AgentCore Memory

Row last verified 2026-05-14. Catalog data is CC-BY-4.0 — see how to read this.